Web & Data

Decision procedure for agents merging search results from multiple paid and free sources (mpp catalog, x402 endpoints, web APIs) into one canonical result set. Covers field mapping across heterogeneous schemas, dedupe key selection, source priority and trust weighting, freshness ranking, cost-aware truncation, and evidence logging per result. Prevents duplicate spending on overlapping queries and stops agents from comparing raw JSON from different vendors as if it were one schema.

Traduce una instrucción en lenguaje natural a una estructura/contrato densa y accionable. input=texto.

Validates text integrity and generates Zero-Knowledge Proofs (ZKPs). Enterprise-grade ZKP security.

Search the indexed public-domain book corpus by title or author substring. Returns matching books ranked by historical popularity with book_id for drill-down into metadata, chapters, quotes, or full-text search. No license, no API key required.

Full-text search across the entire indexed public-domain corpus. Returns the most relevant passages from any book with title/author citations, ranked by relevance. The premium cross-corpus retrieval route — no LLM generation, real excerpts with sources. No license, no API key required.

Look up full metadata for one indexed book by book_id: title, author, year, subjects, bookshelves, download rank, chunk count, and detected chapter range. Use book_id from /book-search or a category shelf. No license, no API key required.

Deterministic daily book pick from the indexed corpus, date-seeded so every caller gets the same answer on the same day. Optional date override for backfill. Returns book_id and drill-down routes. No license, no API key required.

Curated shelf of public-domain adventure fiction, ranked by historical popularity. Returns title, author, year, book_id, and drill-down routes for full-text retrieval. No license, no API key required.

Curated shelf of public-domain children's and young-adult classics, ranked by historical popularity. Returns title, author, year, book_id, and drill-down routes for full-text retrieval. No license, no API key required.

Retrieve a specific contact's full profile by ID.

Returns geographic regions within the United States.

Returns complete historical chart data for a specified datetime timestamp.

OCR: extrae el texto de una imagen (JPG/PNG) o de un PDF, incluidos PDFs escaneados sin capa de texto. Motor local (Tesseract 5), idiomas español e inglés. Sube el archivo por multipart (campo 'archivo') o mándalo como 'archivo_b64' en el JSON. Opcional 'lang' (spa|eng|spa+eng).

Generates random cryptographic proofs or verifiable random outputs.

Generate deterministic related SEO query variants

Verifica una afirmación (fact-check) con veredicto y razón. Nivel verificación. input=afirmación.

One-shot look at a source. No watch is created. Types: url (current page text), rss (latest feed items), price (current USD price), edgar (recent SEC filings — 8-K item codes decoded, Form 4 insider trades parsed into who bought/sold, how much, and whether scheduled). To keep watching, POST /watches with the same body.

Get available location values for lookalikes filtering.

Retrieves advertising demand data based on user intent signals.

Analyzes the health and quality metrics of a GitHub repository.

Extract embedded text from a public PDF URL or multipart upload for research and retrieval pipelines. Returns text, page count, and character count; scanned-image OCR is not included. Remote and uploaded PDFs are limited to the operator-configured maximum size.

Repara/valida JSON roto y lo devuelve limpio. Herramienta dev de alto volumen. input=JSON o texto.

Retrieves or validates sealed data structures or cryptographic seals.

Convierte un texto en un vector (embedding) para búsqueda semántica, RAG, clustering o memoria. El bloque base que todo agente de IA necesita. Alto volumen. input=texto.